Generation Of Applications Research Articles

Key frame extraction algorithm for surveillance videos using an evolutionary approach

With rapid technological advancements, videos are captured, stored, and shared in multiple formats, increasing the requirement for summarization techniques to enable shorter viewing durations. Key Frame Extraction (KFE) algorithms are crucial in video summarization, compression, and offline analysis. This study aims to develop an efficient KFE approach for generic videos. Existing methods include the Adaptive Key Frame Extraction Algorithm, which reduces redundancy while ensuring maximum content coverage; the Optimal Key Frame Extraction Algorithm, which utilizes a Genetic Algorithm (GA) to select key frames optimally; and the Rapid Key Frame Extraction Algorithm, which employs clustering techniques to identify typical key frames. However, a clear prerequisite remains for a more versatile KFE technique that can address generic applications rather than specific use cases. Evolutionary algorithms offer a powerful solution for achieving optimal KFE. This proposed method leverages an interactive GA with a well-designed Fitness Function and elitism-based survivor selection to enhance performance. This proposed algorithm has been tested on diverse datasets, including VSUMM, SumMe, Mall, user-generated videos, surveillance footage from Amrita Vishwa Vidyapeetham University (Coimbatore, India), and web-sourced videos. The results demonstrate that the proposed KFE approach adheres to benchmark data and captures additional significant frames. Compared to Differential Evolution (DE) techniques and Deep Learning (DL) models from the literature, this recommended algorithm demonstrates superior efficiency, as verified through quantitative and qualitative evaluation metrics. Furthermore, the computational complexity of the GA is intricately compared to that of DE and DL-based approaches, highlighting the distinct efficiencies and performance features.

Cadabra and python algorithms in general relativity and cosmology I: Generalities

The aim of this work is to present a series of concrete examples which illustrate how the computer algebra system Cadabra can be used to manipulate expressions appearing in General Relativity and other gravitational theories. We highlight the way in which Cadabra's philosophy differs from other systems with related functionality. The use of various new built-in packages is discussed, and we show how such packages can also be created by end-users directly using the notebook interface. The current paper focuses on fairly generic applications in gravitational theories, including the use of differential forms, the derivation of field equations and the construction of their solutions.

Neural network-assisted generic predictive models of safety factor and yield acceleration for seismic slope stability and displacement assessments

As two well-recognized approaches for seismic slope stability assessment, the pseudo-static analysis estimates the factor of safety (FS) and the Newmark-type analysis estimates permanent downslope-displacement based on input yield acceleration (ky). However, FS and ky are usually obtained from non-trivial slope stability calculations, which can become computationally demanding in probabilistic analyses or regional landslide mapping. This study presents neural network-assisted predictive models for (1) seismic or static FS and the category of failure mode; and (2) ky and the thickness of failure mass. Extensive stability analyses of more than 741,000 and 123,000 slope configurations are conducted to compile datasets of FS and ky, respectively. Performance evaluations indicate that the models produce physically reasonable prediction trends and have good generalization capability with correlation coefficient higher than 0.94 in blind tests. Compared to the existing infinite slope model and predictive tools, the new models achieve improved applicability and functionality, accounting for pore-water pressure, depth to hard stratum, and various failure modes. Both the spreadsheet and MATLAB files established in this study are provided to facilitate generic applications. Therefore, this work not only demonstrates the neural network capability, but also provides useful tools for practitioners, contributing to both the pseudo-static and Newmark-type approaches.

Circumventing traps in analog quantum machine learning algorithms through co-design

Quantum machine learning algorithms promise to deliver near-term, applicable quantum computation on noisy, intermediate-scale systems. While most of these algorithms leverage quantum circuits for generic applications, a recent set of proposals, called analog quantum machine learning (AQML) algorithms, breaks away from circuit-based abstractions and favors leveraging the natural dynamics of quantum systems for computation, promising to be noise-resilient and suited for specific applications such as quantum simulation. Recent AQML studies have called for determining best ansatz selection practices and whether AQML algorithms have trap-free landscapes based on theory from quantum optimal control (QOC). We address this call by systematically studying AQML landscapes on two models: those admitting black-boxed expressivity and those tailored to simulating a specific unitary evolution. Numerically, the first kind exhibits local traps in their landscapes, while the second kind is trap-free. However, both kinds violate QOC theory’s key assumptions for guaranteeing trap-free landscapes. We propose a methodology to co-design AQML algorithms for unitary evolution simulation using the ansatz’s Magnus expansion. Our methodology guarantees the algorithm has an amenable dynamical Lie algebra with independently tunable terms. We show favorable convergence in simulating dynamics with applications to metrology and quantum chemistry. We conclude that such co-design is necessary to ensure the applicability of AQML algorithms.

Use of Deep-Learning-Accelerated Gradient Approximation for Reservoir Geological Parameter Estimation

The estimation of space-varying geological parameters is often not computationally affordable for high-dimensional subsurface reservoir modeling systems. The adjoint method is generally regarded as an efficient approach for obtaining analytical gradient and, thus, proceeding with the gradient-based iteration algorithm; however, the infeasible memory requirement and computational demands strictly prohibit its generic implementation, especially for high-dimensional problems. The autoregressive neural network (aNN) model, as a nonlinear surrogate approximation, has gradually received increasing popularity due to significant reduction of computational cost, but one prominent limitation is that the generic application of aNN to large-scale reservoir models inevitably poses challenges in the training procedure, which remains unresolved. To address this issue, model-order reduction could be a promising strategy, which enables us to train the neural network in a very efficient manner. A very popular projection-based linear reduction method, i.e., propel orthogonal decomposition (POD), is adopted to achieve dimensionality reduction. This paper presents an architecture of a projection-based autoregressive neural network that efficiently derives an easy-to-use adjoint model by the use of an auto-differentiation module inside the popular deep learning frameworks. This hybrid neural network proxy, referred to as POD-aNN, is capable of speeding up derivation of reduced-order adjoint models. The performance of POD-aNN is validated through a synthetic 2D subsurface transport model. The use of POD-aNN significantly reduces the computation cost while the accuracy remains. In addition, our proposed POD-aNN can easily obtain multiple posterior realizations for uncertainty evaluation. The developed POD-aNN emulator is a data-driven approach for reduced-order modeling of nonlinear dynamic systems and, thus, should be a very efficient modeling tool to address many engineering applications related to intensive simulation-based optimization.

Testing and Evaluation of Health Care Applications of Large Language Models

Large language models (LLMs) can assist in various health care activities, but current evaluation approaches may not adequately identify the most useful application areas. To summarize existing evaluations of LLMs in health care in terms of 5 components: (1) evaluation data type, (2) health care task, (3) natural language processing (NLP) and natural language understanding (NLU) tasks, (4) dimension of evaluation, and (5) medical specialty. A systematic search of PubMed and Web of Science was performed for studies published between January 1, 2022, and February 19, 2024. Studies evaluating 1 or more LLMs in health care. Three independent reviewers categorized studies via keyword searches based on the data used, the health care tasks, the NLP and NLU tasks, the dimensions of evaluation, and the medical specialty. Of 519 studies reviewed, published between January 1, 2022, and February 19, 2024, only 5% used real patient care data for LLM evaluation. The most common health care tasks were assessing medical knowledge such as answering medical licensing examination questions (44.5%) and making diagnoses (19.5%). Administrative tasks such as assigning billing codes (0.2%) and writing prescriptions (0.2%) were less studied. For NLP and NLU tasks, most studies focused on question answering (84.2%), while tasks such as summarization (8.9%) and conversational dialogue (3.3%) were infrequent. Almost all studies (95.4%) used accuracy as the primary dimension of evaluation; fairness, bias, and toxicity (15.8%), deployment considerations (4.6%), and calibration and uncertainty (1.2%) were infrequently measured. Finally, in terms of medical specialty area, most studies were in generic health care applications (25.6%), internal medicine (16.4%), surgery (11.4%), and ophthalmology (6.9%), with nuclear medicine (0.6%), physical medicine (0.4%), and medical genetics (0.2%) being the least represented. Existing evaluations of LLMs mostly focus on accuracy of question answering for medical examinations, without consideration of real patient care data. Dimensions such as fairness, bias, and toxicity and deployment considerations received limited attention. Future evaluations should adopt standardized applications and metrics, use clinical data, and broaden focus to include a wider range of tasks and specialties.

Fractional Reverse Inequalities Involving Generic Interval-Valued Convex Functions and Applications

The relation between fractional calculus and convexity significantly impacts the development of the theory of integral inequalities. In this paper, we explore the reverse of Minkowski and Hölder’s inequality, unified Jensen’s inequality, and Hermite–Hadamard (H-H)-like inequalities using fractional calculus and a generic class of interval-valued convexity. We introduce the concept of I.V-(⋏,ℏ) generic class of convexity, which unifies several existing definitions of convexity. By utilizing Riemann–Liouville (R-L) fractional operators and I.V-(⋏,ℏ) convexity to derive new improvements of the H-H- and Fejer and Pachpatte-like inequalities. Our results are quite unified; by substituting the different values of parameters, we obtain a blend of new and existing inequalities. These results are fruitful for establishing bounds for I.V R-L integral operators. Furthermore, we discuss various implications of our findings, along with numerical examples and simulations to enhance the reliability of our results.

Effective generic freeness and applications to local cohomology

AbstractLet be a Noetherian domain and be a finitely generated ‐algebra. We study several features regarding the generic freeness over of an ‐module. For an ideal , we show that the local cohomology modules are generically free over under certain settings where is a smooth ‐algebra. By utilizing the theory of Gröbner bases over arbitrary Noetherian rings, we provide an effective method to b make explicit the generic freeness over of a finitely generated ‐module.

Aspects of complexity in quality and safety assessment of peptide therapeutics and peptide-related impurities. A regulatory perspective

In recent years, a number of therapeutic peptides have been authorized in the EU market, and several others are in the clinical development phase or under assessment for full dossier or generic applications. Quality and safety guidelines specific to peptides are limited, and some aspects have to be considered. In particular, concerns relate to the analytical investigation for impurities and the toxicological assessment of these substances. The guidelines and the compendial pharmacopoeias provide certain references but that may be questionable if interpreted according to whether therapeutic peptides are considered chemical or biological entities, large or small. The characterization of peptide-related impurities cannot follow the small molecule approach but should consider aspects closely linked to the complex mechanisms of action that these large molecules can exert in the human body. Although direct genotoxic mechanisms cannot be excluded, hazardous interactions on biological systems cannot be ruled out, as in the case of natural peptide toxins and their specific interactions with cellular or membrane targets. From a regulatory perspective, only after specific risk identification and characterization should an equally specific safety threshold in relation to potential toxicity be defined.

Some Classical Inequalities Associated with Generic Identity and Applications

In this paper, we derive a new generic equality for the first-order differentiable functions. Through the utilization of the general identity and convex functions, we produce a family of upper bounds for numerous integral inequalities like Ostrowski’s inequality, trapezoidal inequality, midpoint inequality, Simpson’s inequality, Newton-type inequalities, and several two-point open trapezoidal inequalities. Also, we provide the numerical and visual explanation of our principal findings. Later, we provide some novel applications to the theory of means, special functions, error bounds of composite quadrature schemes, and parametric iterative schemes to find the roots of linear functions. Also, we attain several already known and new bounds for different values of γ and parameter ξ.

Small scale CO2 based trigeneration plants in heat recovery applications: A case study for residential sector in northern Italy

This study investigates the potential of trigeneration systems utilizing CO2-based power cycles to harness high-temperature excess heat. Various CO2-based cycles are proposed, comprising pure CO2 and CO2-mixture, emphasizing integration into district heating and cooling networks. Given the non-isothermal heat rejection of CO2-based cycles, performance maps for absorption chillers at different thermal levels and temperature drop of the heat source are generated. These maps are beneficial not only for the current study but also for generic applications. Various cycle layouts are studied, employing strategies to maximize overall electrical efficiency, electrical power output, or thermal production, starting from available high-grade heat above 500 °C. Depending on the specific cycle layout and strategy, the optimal cycle-thermal user coupling is evaluated. The economic and environmental viability of the proposed solution is evaluated in comparison to an existing case-study in northern Italy where the exhaust gases of 10 MWel gas turbines are currently exploited for district heating purposes and centralized vapour-compression chillers meet the residential cooling demand. Compared to the case-study, the adoption of a simple recuperative CO2-mixture bottoming cycle, at a minimum cycle temperature of 70 °C, allows not only a primary energy saving of 16 % but also an 8 % reduction of levelized cost of electricity.

Collaborative credentials for the Internet of Things

The Self-Sovereign Identity (SSI) paradigm has emerged as a decentralized Identity Management model with interesting capabilities for the Internet of Things (IoT). However, current standard SSI protocols and procedures only consider that individuals store their own identity, failing to provide an accurate solution for the identity management of groups where participants might use credentials from different identities and collaborate to meet a set of verifier´s requirements. The present work introduces the concept of Collaborative Credentials (CCs) to formalize identity management procedures that model the collaboration within a group of participants. CCs allow to leverage use cases requiring collaboration that cannot be solved with standard SSI verifiable credentials, increase the privacy of group participants and enable the development of a software framework that any verifier/holder could use to generate a generic application. In the paper, a generic model for CCs is presented, together with an implementation example that is subsequently evaluated in an experimental testbed.

Inferring the Evolutionary Model of Community-Structuring Traits with Convolutional Kitchen Sinks.

When communities are assembled through processes such as filtering or limiting similarity acting on phylogenetically conserved traits, the evolutionary signature of those traits may be reflected in patterns of community membership. We show how the model of trait evolution underlying community-structuring traits can be inferred from community membership data using both a variation of a traditional eco-phylogenetic metric-the mean pairwise phylogenetic distance (MPD) between taxa-and a recent machine learning tool, Convolutional Kitchen Sinks (CKS). Both methods perform well across a range of phylogenetically informative evolutionary models, but CKS outperforms MPD as tree size increases. We demonstrate CKS by inferring the evolutionary history of freeze tolerance in angiosperms. Our analysis is consistent with a late burst model, suggesting freeze tolerance evolved recently. We suggest that multiple data types that are ordered on phylogenies, such as trait values, species interactions, or community presence/absence, are good candidates for CKS modeling because the generative models produce structured differences between neighboring points that CKS is well-suited for. We introduce the R package kitchen to perform CKS for generic application of the technique.

Automatic classification of smart sensor data for evaluating machine tool efficiency

The assessment of production plant efficiency is crucial for optimizing the operational performance of manufacturing systems. In traditional facilities, automated data collection is limited and information primarily relies on operators declarations, which are prone to inaccuracy. There is therefore a need for readily accessible digital alternatives. This paper introduces a cost-effective method for classifying the status of machine tools using smart sensors to monitor their primary doors with minimal integration, and a streamlined algorithm for efficient data processing. The innovative algorithm was conceived using data collected in over 3 months in a manufacturing plant comprising 50 diverse machine tools engaged in batch production for the automotive industry, and is based on non-dimensional thresholds, making it suitable for generic applications requiring classification of repetitive patterns. Also, a realistic simulator was developed to provide reliable data for algorithm accuracy evaluation. The classification performance was fully tested using synthetic data, showing very good accuracy. In addition, the performance of the algorithm was compared to basic machine learning approaches further proving the validity of the proposed method. Ultimately, the classification algorithm was employed to assess the Overall Equipment Effectiveness (OEE) of the real plant machines, which were closely aligned with the estimates provided by the enterprise management.

Day–Night architecture: Development of an ultra-low power RISC-V processor for wearable anomaly detection

In healthcare, anomaly detection has emerged as a central application. This study presents an ultra-low power processor tailored for wearable devices dedicated to anomaly detection. Introducing a unique Day–Night architecture, the processor is bifurcated into two distinct segments: The Day segment and the Night segment, both of which function autonomously. The Day segment, catering to generic wearable applications, is designed to remain largely inactive, awakening only for specific tasks. This approach leads to considerable power savings by incorporating the Main-CPU and system interconnect, both major power consumers. Conversely, the Night segment is dedicated to real-time anomaly detection using sensor data analytics. It comprises a Sub-CPU and a minimal set of IPs, operating continuously but with minimized power consumption. To further enhance this architecture, the paper presents an ultra-lightweight RISC-V core, All-Night core, specialized for anomaly detection applications, replacing the traditional Sub-CPU. To validate the Day–Night architecture, we developed a prototype processor and implemented it on an FPGA board. An anomaly detection application, optimized for this prototype, was also developed to showcase its functional prowess. Finally, when we synthesized the processor prototype using 45 nm process technology, it affirmed our assertion of achieving an energy reduction of up to 57%.

Assessment of an auto-routing method for topology generation of aircraft power supply systems

During early phases of aircraft development, overall systems design is performed to estimate relevant system design parameters such as mass, power consumption, and compliance with architectural requirements (redundancy). The GeneSys software framework has been developed for parametric modeling of aircraft on-board systems for overall systems design. To this end, model-based architecture definition, topology generation (components positioning and connections routing), and system sizing are conducted. The topology generation is currently performed using design templates containing knowledge-based heuristics derived from systems topologies of existing aircraft. However, using such design templates limits their generic application to novel aircraft models because exceptions for geometric differences between these models need to be implemented. This especially applies to the topology generation of power supply systems (electric, hydraulic) due to their high number of interfaces to consumer systems. To overcome these limitations, an automated routing method is presented in this paper as a generic approach for topology generation. With this method, the system topology is generated based on a defined routing network, which comprises areas of the aircraft for allowed components positioning and connections routing. Using Dijkstra’s algorithm, the shortest path connections are found within the established routing network. Furthermore, boundary conditions for routing, for instance adding a cost function for power segregation, can be defined. An assessment of the automated routing method applied on the electric power supply system is performed using qualitative parameters such as the capability to adapt the routing network. Quantitative parameters like cable length and system mass are assessed as well.

Tensor-based multi-view spectral clustering via shared latent space

Multi-view Spectral Clustering (MvSC) partitions data into clusters according to multiple views for higher performance. However, most existing works overlook model interpretability and involve iterative and alternating updates on parameters with expensive computations, where out-of-sample predictions are also commonly prohibitive. In this paper, we construct a novel weighted conjugate feature duality for formulating the MvSC problem cast as a weighted principal components analysis. In this new method, a common latent space is derived with shared dual variables, which achieves the couplings by learning projections from different views into the latent space. To boost higher-order correlations, the tensor-based modeling is introduced. Our method leads to a closed-form solution in the dual through a single eigendecomposition thanks to the primal–dual representation, leading to easy algorithmic setups in practice. Our novel conjugate duality and the conceived shared latent space greatly boost the efficiency in model representation and computation: element-wise operations of kernels are involved in the dual instead of the explicit tensor computation in the primal and the size of our eigendecomposition is independent of the number of views. Besides, we can effectively incorporate the visualization of the clusters in a single latent space, which is particularly useful with many data views. For predicting unseen data under generic applications, our method can be flexibly applied with out-of-sample extensions, which can also be utilized for further efficiency in large-scale cases with fixed-size kernel schemes. Numerical experiments verify our superiority in accuracy, efficiency, and diverse data explorations.

Multi-view Image Fusion Using Ensemble Deep Learning Algorithm For MRI And CT Images

Medical image fusions are crucial elements in image-based health care diagnostics or therapies and generic applications of computer visions. However, the majority of existing methods suffer from noise distortion that affects the overall output. When pictures are distorted by noises, classical fusion techniques perform badly. Hence, fusion techniques that properly maintain information comprehensively from multiple faulty pictures need to be created. This work presents Enhanced Lion Swarm Optimization (ESLO) with Ensemble Deep Learning (EDL) to address the aforementioned issues. The primary steps in this study include image fusions, segmentation, noise reduction, feature extraction, picture classification, and feature selection. Adaptive Median Filters are first used for noise removal in sequence to enhance image quality by eliminating noises. The MRIs and CT images are then segmented using the Region Growing–based k -Means Clustering (RKMC) algorithm to separate the images into their component regions or objects. Images in black and white are divided into image. In the white image, the RKMC algorithm successfully considered the earlier tumour probability. The next step is feature extraction, which is accomplished by using the Modified Principal Component Analysis (MPCA) to draw out the most informative aspects of the images. Then the ELSO algorithm is applied for optimal feature selection, which is computed by best fitness values. After that, multi-view image fusions of multi modal images derive lower-, middle-, and higher-level image contents. It is done by using Deep Convolution Neural Network (DCNN) and the Tissue-Aware Conditional Generative Adversarial Network (TAcGAN) algorithm, which fuses the multi-view features and relevant image features, and it is used for real-time applications. ELSO +EDL algorithm gives better results in terms of accuracy, Peak Signal-To-Noise Ratio (PSNR), and lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) when compared to other existing algorithms.

Design of an economic, portable, compact, and indigenous instrument setup for measuring sensing characteristics of thin film gas sensors.

Thin film gas sensor characterization is very demanding for various applications because of technical design trade-offs in commercially available gas sensors. For gas sensing characterization, a suitable gas-testing experimental setup is very much needed in this context. Various factors in the experimental setup can affect a thin film gas sensor's response beyond gas exposure. These factors include the test chamber's volume, relative humidity, uniform operating temperature, uniform pressure, uniform gas density, uniform gas distribution, uniform gas concentration in the gas chamber, and uniform relative gas flow velocity over the surface of the sensor. All these environmental parameters, not being so predictive in nature, induce an inherent design trade-off in the experimental setup design. Although all the commercially available gas testing experimental setups are equally good considering the dedicated purpose for which they are made. However, all of them are for generic applications but not for specific applications because of their inherent trade-offs in their usability features. Those trade-offs always provide an opportunity to introduce a new setup with its own unique advantages. Hence, in this article, we have presented a portable, compact, indigenous gas sensing experimental setup for studying the performance of gas sensors. We have characterized and tested the setup using a ZnO based thin film gas sensor when exposed to CO2 gas at concentrations ranging from 1445 to 4631 ppm. The proposed gas sensing setup's compact size offers unique advantages, including portability and compatibility for uniform environmental conditions.

Immunocapture LC-MS methods for pharmacokinetics of large molecule drugs.

Implementation of immunocapture LC-MS methods to characterize the pharmacokinetic profile of large molecule drugs has become a widely used technique over the past decade. As the pharmaceutical industry strives for speediness into clinical development without jeopardizing quality, robust assays with generic application across the pipeline are becoming instrumental in bioanalysis, especially in early-stage development. This review highlights the capabilities and challenges involved in hybrid immunocapture LC-MS techniques and its continued applications in nonclinical and clinical pharmacokinetic assay design. This includes a comparison of LC-MS-based approaches to conventional ligand-binding assays and the driving demands in large molecule drug portfolios including growing sensitivity requirements and the unique challenges of new modalities requiring innovation in the bioanalytical laboratory.